atom feed47 messages in org.freebsd.freebsd-currentRe: Some performance measurements on ...
FromSent OnAttachments
Luigi RizzoApr 19, 2012 6:12 am 
Slawa OlhovchenkovApr 19, 2012 11:53 am 
Andre OppermannApr 19, 2012 1:05 pm 
Luigi RizzoApr 19, 2012 1:26 pm 
K. MacyApr 19, 2012 1:34 pm 
Luigi RizzoApr 19, 2012 2:03 pm 
K. MacyApr 19, 2012 2:06 pm 
Andre OppermannApr 19, 2012 2:11 pm 
K. MacyApr 19, 2012 2:17 pm 
Andre OppermannApr 19, 2012 2:19 pm 
Andre OppermannApr 19, 2012 2:26 pm 
K. MacyApr 19, 2012 2:35 pm 
K. MacyApr 19, 2012 2:36 pm 
Luigi RizzoApr 19, 2012 2:43 pm 
Andre OppermannApr 19, 2012 3:36 pm 
Luigi RizzoApr 19, 2012 11:16 pm 
Alexander V. ChernikovApr 20, 2012 1:26 am 
Andre OppermannApr 20, 2012 2:00 am 
Andre OppermannApr 20, 2012 2:25 am 
John BaldwinApr 20, 2012 5:11 am 
Luigi RizzoApr 20, 2012 7:26 am 
K. MacyApr 20, 2012 9:28 am 
Luigi RizzoApr 20, 2012 11:46 am 
Bruce EvansApr 20, 2012 11:33 pm 
Adrian ChaddApr 21, 2012 7:14 pm 
K. MacyApr 22, 2012 7:04 am 
Andre OppermannApr 24, 2012 6:16 am 
Luigi RizzoApr 24, 2012 6:44 am 
Li, QingApr 24, 2012 7:15 am 
K. MacyApr 24, 2012 8:03 am 
K. MacyApr 24, 2012 8:05 am 
Luigi RizzoApr 24, 2012 9:16 am 
K. MacyApr 24, 2012 9:18 am 
Fabien ThomasApr 24, 2012 9:34 am 
Li, QingApr 24, 2012 10:39 am 
Li, QingApr 24, 2012 10:42 am 
Bjoern A. ZeebApr 24, 2012 5:01 pm 
Maxim KonovalovApr 25, 2012 2:21 am 
Slawa OlhovchenkovApr 25, 2012 3:19 am 
K. MacyApr 25, 2012 8:44 am 
Bjoern A. ZeebApr 25, 2012 11:53 am 
George Neville-NeilMay 1, 2012 7:27 am 
Luigi RizzoMay 1, 2012 8:21 am 
George Neville-NeilMay 1, 2012 10:33 am 
Bjoern A. ZeebMay 1, 2012 2:08 pm 
Luigi RizzoMay 1, 2012 2:22 pm 
Luigi RizzoMay 3, 2012 9:32 am 
Subject:Re: Some performance measurements on the FreeBSD network stack
From:K. Macy (kma@freebsd.org)
Date:Apr 19, 2012 2:36:56 pm
List:org.freebsd.freebsd-current

On Thu, Apr 19, 2012 at 11:27 PM, Andre Oppermann <and@freebsd.org> wrote:

On 19.04.2012 23:17, K. Macy wrote:

This only helps if your flows aren't hitting the same rtentry. Otherwise you still convoy on the lock for the rtentry itself to increment and decrement the rtentry's reference count.

The rtentry lock isn't obtained anymore.  While the rmlock read lock is held on the rtable the relevant information like ifp and such is copied out.  No later referencing possible.  In the end any referencing of an rtentry would be forbidden and the rtentry lock can be removed.  The second step can be optional though.

Can you point me to a tree where you've made these changes?

It's not in a public tree.  I just did a 'svn up' and the recent pf and rtsocket changes created some conflicts.  Have to solve them before posting.  Timeframe (early) next week.

Ok. Keep us posted.

Thanks, Kip

--    “The real damage is done by those millions who want to 'get by.' The ordinary men who just want to be left in peace. Those who don’t want their little lives disturbed by anything bigger than themselves. Those with no sides and no causes. Those who won’t take measure of their own strength, for fear of antagonizing their own weakness. Those who don’t like to make waves—or enemies.

   Those for whom freedom, honour, truth, and principles are only literature. Those who live small, love small, die small. It’s the reductionist approach to life: if you keep it small, you’ll keep it under control. If you don’t make any noise, the bogeyman won’t find you.

   But it’s all an illusion, because they die too, those people who roll up their spirits into tiny little balls so as to be safe. Safe?! From what? Life is always on the edge of death; narrow streets lead to the same place as wide avenues, and a little candle burns itself out just like a flaming torch does.

   I choose my own way to burn.”

   Sophie Scholl